Papers with Code 아카이브
Visual Dialog
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 98
Visual Dialog requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a follow-up question about the image, the task is to answer the question.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Enhancing Visual Dialog State Tracking through Iterative Object-Entity Alignment in Multi-Round Conversations
ICCV23 Visual-Dialog Emotion Explanation Challenge: SEU_309 Team Technical Report
Hawk: Learning to Understand Open-World Video Anomalies
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
FlexCap: Describe Anything in Images in Controllable Detail
$\mathbb{VD}$-$\mathbb{GR}$: Boosting $\mathbb{V}$isual $\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\mathbb{GR}$aphs
Collecting Visually-Grounded Dialogue with A Game Of Sorts
Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations
PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
Unified Multimodal Model with Unlikelihood Training for Visual Dialog
A survey on knowledge-enhanced multimodal learning
LAVIS: A Library for Language-Vision Intelligence
Video Dialog as Conversation about Objects Living in Space-Time
Adversarial Robustness of Visual Dialog
VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution
The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training
UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning
Reasoning with Multi-Structure Commonsense Knowledge in Visual Dialog
Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene
Modeling Coreference Relations in Visual Dialog
VU-BERT: A Unified framework for Visual Dialog
Discourse Analysis for Evaluating Coherence in Video Paragraph Captions
UNITER-Based Situated Coreference Resolution with Rich Multimodal Input
Perceptual Score: What Data Modalities Does Your Model Perceive?
ViDA-MAN: Visual Dialog with Digital Humans
Evaluating and Improving Interactions with Hazy Oracles
GoG: Relation-aware Graph-over-Graph Network for Visual Dialog
Learning to Ground Visual Objects for Visual Dialog
Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser
Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation
Ensemble of MRR and NDCG models for Visual Dialog
Where Are You? Localization from Embodied Dialog
Reasoning Over History: Context Aware Visual Dialog
Multi-Modal Open-Domain Dialogue
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.